Skip to main content
Glama
KitchenSink4AI

io.github.nometalalchemist/kitchensink4xl

by KitchenSink4AI
OverviewSchemaSourceRelated ServersScoreDiscussionsAdmin
Python
Local

validate

Read-only

Run read-only correctness checks on Excel workbooks to detect broken references, formula errors, merge conflicts, and structural issues, then return a pass/fail report with detailed findings.

Instructions

Run read-only correctness checks and return one report. checks (default ['structure', 'references', 'calc_staleness']): structure (package opens clean, sheet integrity), references (#REF!/#NAME? and the other error cells), names (broken defined names), merges (overlapping or orphaned merged ranges), tables (duplicate names, broken refs, overlaps), formatting_bloat (the audit_styles counters against the 64,000-format ceiling), hazards (the round-trip scan as a check), external_links (links reported, not repaired), calc_staleness (formulas lacking cached values, which read as blank outside Excel). Returns {passed, results: {check: {passed, findings}}}; findings keep the underlying ops' shapes where those exist, and passed=false means findings, not a failed call. Read-only, always; repairs live in the editing tools. Works while the file is open in Excel.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathYes
checksNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.2.0
    • changedOutput schema / (root)
      Previous value: -{
-  "additionalProperties": true,
-  "type": "object"
-}New value: +null
  2. First observedv1.0.0

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotation readOnlyHint=true is reinforced and expanded: 'Read-only, always' plus 'passed=false means findings, not a failed call.' It also discloses important behavior like working while the file is open and external links being reported but not repaired, which goes well beyond the annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but every sentence carries necessary information: the main purpose is front-loaded, the check list is compactly parenthesized, and the return semantics and read-only behavior are stated without filler. The length is justified by the absence of enums in the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and minimal input schema, the description provides everything needed: parameter values, default behavior, return shape, the meaning of passed=false, and operating constraints. There are no significant gaps for an agent selecting or invoking this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description fully compensates. It explains the required path parameter implicitly, lists every valid check name with a one-line meaning, and states the default check set. Without this, an agent would have no idea what values 'checks' accepts.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+resource: 'Run read-only correctness checks and return one report.' It then enumerates exactly which checks are included, which distinguishes it from sibling editing/diagnostic tools and makes its purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It clearly frames when to use the tool: for read-only correctness validation, and it explicitly says 'repairs live in the editing tools,' so an agent knows not to use this for fixes. It does not name a specific sibling alternative, but the context is clear enough that this is the validation entry point.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools